docs: add ANE float16 beeping issue to iOS CoreML issues#16
Merged
Alex-Wengg merged 2 commits intomainfrom Jan 31, 2026
Merged
Conversation
Alex-Wengg
pushed a commit
that referenced
this pull request
Feb 3, 2026
`torch.no_grad` is thread local, I now run the autoregressive generation in a separate thread, in addition of the thread running mimi, and forgot to add `torch.no_grad` to the function inside this thread.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
IOS_COREML_ISSUES.md: ANE float16 precision loss causes audible beeping in Mimi decoder streaming outputContext
The Mimi decoder has 23 streaming state tensors fed back every 80ms. When running on the ANE (native float16), precision errors compound across frames in overlap-add buffers and attention caches, producing beeping artifacts. Switching to
.cpuAndGPUfor the Mimi decoder specifically fixes the issue while keeping other models on ANE for performance.